Instructions to use NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO")
model = AutoModelForCausalLM.from_pretrained("NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO

SGLang

How to use NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO with Docker Model Runner:
```
docker model run hf.co/NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO
```

No responses

by emilios - opened Mar 4, 2024

Discussion

emilios

Mar 4, 2024

•

edited Mar 4, 2024

Hello world

Today I cannot get any response from the model. Can someone please look into it

No output was generated. Something went wrong

emilios

Mar 4, 2024

Also

Something went wrong while requesting the Inference API: "Model NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO time out"

teknium

NousResearch org Mar 4, 2024

Hello world

Today I cannot get any response from the model. Can someone please look into it

No output was generated. Something went wrong

Where can you not get response from?

teknium

NousResearch org Mar 4, 2024

Also

Something went wrong while requesting the Inference API: "Model NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO time out"

Yes thats due to a new huggingface feature that allows chatting with the model on the model card, it comes back 15 minutes or so after updating readme

emilios

Mar 4, 2024

Than you.

Yes the second response was from the model page

On the spaces it just timed out and on chat assistants it gave the first response I ve mentioned

Now all are good, thank you:)

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment